Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xue, Xi, Suzuki, Kunio, Goswami, Nabarun, Shintate, Takuya
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909716038287360
author Xue, Xi
Suzuki, Kunio
Goswami, Nabarun
Shintate, Takuya
author_facet Xue, Xi
Suzuki, Kunio
Goswami, Nabarun
Shintate, Takuya
contents The rapid advancement of diffusion-based video generation models has led to increasingly realistic synthetic content, presenting new challenges for video forgery detection. Existing methods often struggle to capture fine-grained temporal inconsistencies, particularly in AI-generated videos with high visual fidelity and coherent motion. In this work, we propose a detection framework that leverages spatial-temporal consistency by combining RGB appearance features with optical flow residuals. The model adopts a dual-branch architecture, where one branch analyzes RGB frames to detect appearance-level artifacts, while the other processes flow residuals to reveal subtle motion anomalies caused by imperfect temporal synthesis. By integrating these complementary features, the proposed method effectively detects a wide range of forged videos. Extensive experiments on text-to-video and image-to-video tasks across ten diverse generative models demonstrate the robustness and strong generalization ability of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00397
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency
Xue, Xi
Suzuki, Kunio
Goswami, Nabarun
Shintate, Takuya
Computer Vision and Pattern Recognition
The rapid advancement of diffusion-based video generation models has led to increasingly realistic synthetic content, presenting new challenges for video forgery detection. Existing methods often struggle to capture fine-grained temporal inconsistencies, particularly in AI-generated videos with high visual fidelity and coherent motion. In this work, we propose a detection framework that leverages spatial-temporal consistency by combining RGB appearance features with optical flow residuals. The model adopts a dual-branch architecture, where one branch analyzes RGB frames to detect appearance-level artifacts, while the other processes flow residuals to reveal subtle motion anomalies caused by imperfect temporal synthesis. By integrating these complementary features, the proposed method effectively detects a wide range of forged videos. Extensive experiments on text-to-video and image-to-video tasks across ten diverse generative models demonstrate the robustness and strong generalization ability of the proposed approach.
title Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.00397